MODELING STUDENT KNOWLEDGE STATES USING BAYESIAN KNOWLEDGE TRACING: AN EXPERIMENT WITH THE TOPIC OF SPHERE EQUATIONS
DOI:
https://doi.org/10.18173/2354-1075.2026-0108Keywords:
Bayesian Knowledge Tracing, KT‑IDEM, knowledge tracing, sphere equations, personalized learningAbstract
Personalized learning is increasingly becoming an essential requirement in modern education, driving the need for accurately modeling learners' knowledge states. In this study, we systematically evaluated the traditional Bayesian Knowledge Tracing (BKT) model alongside two of its variants KT‑IDEM (which incorporates item difficulty) and Forgetting BKT (which accounts for knowledge decay) to track student performance on the topic of “Sphere Equations” (Grade 12 Mathematics). Specifically, a web application was developed to collect real interaction data from 143 students, with all 283 questions labeled in detail according to 11 constituent skills. Results from 5-fold cross-validation demonstrated that KT‑IDEM yielded better predictive performance compared to both standard BKT and Forgetting BKT. Furthermore, visualizing knowledge states using the trained model parameters not only helped identify
instances of guessing and slipping but also provided a personalized “competency map” at the individual
skill level, offering valuable support for both teachers and students. These preliminary findings suggest that
KT‑IDEM has the potential to support the diagnosis of students' knowledge states, opening up promising
avenues for building real-time adaptive exercise recommendation systems that contribute to advancing
personalized learning in the Vietnamese educational context.
Downloads
References
- Abdelrahman, G., Wang, Q., & Nunes, B. (2022). Knowledge tracing: A survey. ACM Computing Surveys, 55(11), 1–37. https://doi.org/10.1145/3569576
- Alkhatlan, A., & Kalita, J. (2018). Intelligent tutoring systems: A comprehensive historical survey with recent developments. http://arxiv.org/abs/1812.09628
- Bulut, O., Shin, J., Yildirim-Erbasli, S. N., Gorgun, G., & Pardos, Z. A. (2023). An introduction to Bayesian knowledge tracing with pyBKT. Psych, 5(3), 770–786. https://doi.org/10.3390/psych5030050
- Corbett, A. T., & Anderson, J. R. (1995). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4, 253–278.
- Dai, M., Hung, J., Du, X., Tang, H., & Li, H. (2021). Knowledge tracing: A review of available techniques. Journal of Educational Technology Development and Exchange, 14(2).
- Desmarais, M. C., & Baker, R. S. J. d. (2012). A review of recent advances in learner and skill modeling in intelligent learning environments. User Modeling and User-Adapted Interaction, 22(1–2), 9–38. https://doi.org/10.1007/s11257-011-9106-8
- Khajah, M., Lindsey, R. V., & Mozer, M. C. (2016). How deep is knowledge tracing? http://arxiv.org/abs/1604.02416
- Koedinger, K. R., Corbett, A. T., & Perfetti, C. (2012). The knowledge-learning-instruction framework: Bridging the science-practice chasm to enhance robust student learning. Cognitive Science, 36(5), 757–798. https://doi.org/10.1111/j.1551-6709.2012.01245.x
- Nedungadi, P., & Remya, M. S. (2015). Incorporating forgetting in the personalized, clustered, Bayesian knowledge tracing (PC-BKT) model. In 2015 International Conference on Cognitive Computing and Information Processing (CCIP) (pp. 1–5). https://doi.org/10.1109/CCIP.2015.7100688
- Pardos, Z. A., & Heffernan, N. T. (2011). KT-IDEM: Introducing item difficulty to the knowledge tracing model (pp. 243–254). https://doi.org/10.1007/978-3-642-22362-4_21
- Phạm Hoàng An. (2025). Mô hình truy vết tri thức người học kết hợp động lực thời gian: Phân tích khả năng dự đoán từ SAINT+ và dữ liệu EdNet. Tạp chí Khoa học Trường Đại học Mở Hà Nội, 549. https://doi.org/10.59266/houjs.2025.811
- Shimada, D., & Okada, K. (2025). Reliability coefficient for Bayesian knowledge tracing models. Technology, Knowledge and Learning. https://doi.org/10.1007/s10758-025-09829-7
- Yudelson, M. V., Koedinger, K. R., & Gordon, G. J. (2013). Individualized Bayesian knowledge tracing models (pp. 171–180). https://doi.org/10.1007/978-3-642-39112-5_18



